Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1322 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Captioning | COCO 17 | 23 | Feb 26, 2026 | ||
| Object Pose Estimation | TUD-L BOP (test) | 23 | Feb 26, 2026 | ||
| Text-to-Image Generation | LAION-COCO | 23 | May 18, 2026 | ||
| Event Spotting | FineGym | 23 | Feb 26, 2026 | ||
| Event Spotting | FS-Perf | 23 | Feb 26, 2026 | ||
| Event Spotting | Comp FS | 23 | Feb 26, 2026 | ||
| Image Classification | FGVC Aircraft Air | 23 | Feb 26, 2026 | ||
| Anomaly Detection | VisA 4-shot | 23 | May 18, 2026 | ||
| Anomaly Detection | VisA 1-shot | 23 | May 18, 2026 | ||
| Science Question Answering | GPQA Diamond (test) | 23 | Jul 1, 2026 | ||
| General Tasks | MMLU-Pro | 23 | May 20, 2026 | ||
| OCR-related Parsing Tasks | OmniDocBench English | 23 | Feb 26, 2026 | ||
| Cell type clustering | Curated In-Distribution (ID) (test) | 23 | Jul 7, 2026 | ||
| 3D Gaze Estimation | GFIE (test) | 23 | Mar 6, 2026 | ||
| Pixel-level Anomaly Detection | ClinicDB | 23 | Mar 4, 2026 | ||
| Point Cloud Matching | FAUST_r | 23 | Feb 27, 2026 | ||
| Point Cloud Matching | SCAPE_r | 23 | Feb 27, 2026 | ||
| Retrieval-Augmented Generation | NQ | 23 | Feb 26, 2026 | ||
| Instruction Following | ComplexInstruct Level 6 | 23 | Feb 26, 2026 | ||
| Instruction Following | ComplexInstruct Level 5 | 23 | Feb 26, 2026 | ||
| Instruction Following | ComplexInstruct Level 4 | 23 | Feb 26, 2026 | ||
| Instruction Following | ComplexInstruct Level 3 | 23 | Feb 26, 2026 | ||
| Instruction Following | ComplexInstruct Level 1 | 23 | Feb 26, 2026 | ||
| Reading Comprehension | RC | 23 | Apr 14, 2026 | ||
| Portrait Image Animation | HDTF (test) | 23 | May 28, 2026 |